Tat-seng Chua

13

Papers

216

Total Citations

Papers (13)

Can I Trust Your Answer? Visually Grounded Video Question Answering

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering

Temporally and Distributionally Robust Optimization for Cold-Start Recommendation

Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene

Universal Scene Graph Generation

Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion

Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs

STEP: Enhancing Video-LLMs’ Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation

Discriminative Probing and Tuning for Text-to-Image Generation

Abductive Ego-View Accident Video Understanding for Safe Driving Perception

LASO: Language-guided Affordance Segmentation on 3D Object